CN106844088A - The data transmission method for uplink and device of a kind of RAID storage system - Google Patents

Abstract

The invention discloses a data sending method and device of a RAID storage system. The method includes: receiving a read command sent by a host, and finding a target stripe unit according to the read command; judging the target stripe unit by using a parity check algorithm Whether the data in the target stripe unit is correct; if yes, send the data in the target stripe unit to the host; if not, use the parity check algorithm to restore the data in the target stripe unit, and enter the target stripe unit The step of sending the data to the host. It can be seen that when the RAID storage system receives the read command from the host, it will check the data of the corresponding target stripe unit, and only send the data to the host on the premise of ensuring that the data is correct, which not only avoids wrong data The transmission of data, and more importantly, it can ensure the validity of data transmission and improve the efficiency of transmission.

Description

Data sending method and device of a RAID storage system

technical field

The invention relates to the field of storage systems, in particular to a data sending method and device of a RAID storage system.

Background technique

A RAID storage system includes a controller and multiple disk arrays, the controller is used to execute various instructions sent by the host, and the disk array is used to store data. When receiving the read command sent by the host, the controller will return the data in the corresponding disk array to the host according to the read command.

However, due to improper operation of software and hardware, errors may occur when data is being stored, resulting in that when the host sends a read command, the controller returns wrong data to the host. When the host receives the data returned by the controller, it will perform a corresponding parity check to determine whether the data returned by the controller is correct. If not, it will continue to send a read command to the controller, but the controller does not know the current The stored data is wrong, therefore, the same data will be returned to the host repeatedly, which eventually leads to low efficiency and poor validity for the host to read data.

It can be seen that, when the host sends out a read command, how the controller can quickly and effectively provide correct data to the host, so as to ensure the efficiency and effectiveness of reading is an urgent problem to be solved by those skilled in the art.

Contents of the invention

The purpose of the present invention is to provide a data sending method and device of a RAID storage system, for how the controller can quickly and effectively provide correct data to the host when the host issues a read command, thereby ensuring the efficiency and effectiveness of the read sex.

In order to solve the above-mentioned technical problems, the present invention provides a data transmission method of a RAID storage system, comprising:

receiving the read instruction sent by the host, and finding the target stripe unit according to the read instruction;

Using a parity check algorithm to determine whether the data in the target stripe unit is correct;

If yes, sending the data in the target stripe unit to the host;

If not, recover the data in the target stripe unit by using the parity check algorithm, and enter the step of sending the data in the target stripe unit to the host.

Preferably, the judging whether the data in the target stripe unit is correct by using a parity check algorithm specifically includes:

Reading the stored data of the target stripe unit and the stored first parity data corresponding to the target stripe unit;

generating new first parity data from the stored data of the target stripe unit according to the parity algorithm;

judging whether the stored first parity data is the same as the new first parity data;

Wherein, if yes, enter the step of sending the data in the target stripe unit to the host; recovery steps.

Preferably, the recovering the data in the target stripe unit by using the parity algorithm specifically includes:

Obtain the second parity data of the stripe where the target stripe unit is located and the stored data of the remaining stripe units in the stripe where the target stripe unit is located, and generate the target parity data according to the parity algorithm The new data corresponding to the stripe unit;

generating new data corresponding to the target stripe unit and comparing it with the first parity data according to the parity algorithm;

judging whether the compared first parity data is the same as the stored first parity data;

If so, overwrite the stored data of the target stripe unit with the new data corresponding to the target stripe unit, and enter the step of sending the data in the target stripe unit to the host;

If not, then judging whether the new data corresponding to the target stripe unit is the same as the stored data of the target stripe unit;

If not, output an error message;

If so, modify the first parity data corresponding to each stripe unit of the stripe where the target stripe unit is located according to the parity algorithm, and enter the data in the target stripe unit Steps to send to said host.

Preferably, the judging whether the data in the target stripe unit is correct by using a parity check algorithm specifically includes:

calculating second parity data of the stripe where the target stripe unit is located according to the parity algorithm;

judging whether the calculated second parity data is the same as the stored second parity data;

Wherein, if yes, enter the step of sending the data in the target stripe unit to the host; recovery steps.

Preferably, the recovering the data in the target stripe unit by using the parity algorithm specifically includes:

Setting the first stripe unit of the stripe where the target stripe unit is located as the starting unit;

According to the parity algorithm, generate the current stripe unit from the stored second parity data of the current stripe and the stored first parity data of the remaining stripe units in the stripe where the target stripe unit is located Corresponding new data;

generating a new checksum corresponding to the current stripe from the new data corresponding to the current stripe unit and the stored data of the remaining stripe units in the stripe where the target stripe unit is located;

Judging whether the new checksum corresponding to the current stripe is the same as the existing checksum;

If so, overwrite the stored data of the current stripe unit with the new data corresponding to the current stripe unit, and enter the step of sending the data in the target stripe unit to the host;

If not, determine whether the current stripe unit is the last stripe unit storing data;

If yes, output a message indicating an error; if not, use the next stripe unit of the current stripe unit as the current stripe unit and return.

In order to solve the above-mentioned technical problems, the present invention also provides a data sending device of a RAID storage system, comprising:

A search unit, configured to receive a read instruction sent by the host, and find a target stripe unit according to the read instruction;

A judging unit, configured to use a parity check algorithm to judge whether the data in the target stripe unit is correct;

A recovery unit, configured to use the parity check algorithm to recover the data in the target stripe unit when the determination result of the determination unit is No;

The sending unit is configured to send the data in the target stripe unit to the host when the judging result of the judging unit is yes, or after the restoring unit restores the data.

Preferably, the judging unit specifically includes:

A reading module, configured to read the stored data of the target stripe unit and the stored first parity data corresponding to the target stripe unit;

A first generating module, configured to generate new first parity data from the stored data of the target stripe unit according to the parity algorithm;

The first judging module is used to judge whether the stored first parity data is the same as the new first parity data, if yes, trigger the sending unit, otherwise, trigger the recovery unit.

Preferably, the recovery unit specifically includes:

The second generation module is configured to obtain the second parity data of the stripe where the target stripe unit is located and the stored data of the remaining stripe units of the stripe where the target stripe unit is located, and obtain the parity data according to the parity A verification algorithm generates new data corresponding to the target stripe unit;

A third generating module, configured to generate new data corresponding to the target stripe unit and compare it with the first parity data according to the parity algorithm;

A second judging module, configured to judge whether the compared first parity data is the same as the stored first parity data;

The first covering module is configured to overwrite the stored data of the target stripe unit with the new data corresponding to the target stripe unit when the judgment result of the second judging module is yes, and trigger the sending unit ;

A third judging module, configured to judge whether the new data corresponding to the target stripe unit is the same as the stored data of the target stripe unit when the judging result of the second judging module is No;

The first output module is configured to output information prompting an error when the judgment result of the third judging module is No;

The modification module modifies the first parity data corresponding to each stripe unit of the stripe where the target stripe unit is located according to the parity algorithm when the judgment result of the third judgment module is yes, And trigger the sending unit.

Preferably, the judging unit specifically includes:

a calculation module, configured to calculate the second parity data of the stripe where the target stripe unit is located according to the parity algorithm;

The fourth judging module is used to judge whether the calculated second parity data is the same as the stored second parity data, if yes, trigger the sending unit, otherwise, trigger the recovery unit.

Preferably, the recovery unit specifically includes:

A setting module, configured to set the first strip unit of the strip where the target strip unit is located as the starting unit;

The fourth generating module is configured to convert the stored second parity data of the current stripe and the stored first parity data of the remaining stripe units of the stripe where the target stripe unit is located according to the parity algorithm. Generate new data corresponding to the current stripe unit from the experimental data;

A fifth generating module, configured to generate a new checksum corresponding to the current stripe from the new data corresponding to the current stripe unit and the stored data of the remaining stripe units in the stripe where the target stripe unit is located;

A fifth judging module, configured to judge whether the new checksum corresponding to the current stripe is the same as the existing checksum;

The second covering module is used to overwrite the stored data of the current stripe unit with the new data corresponding to the current stripe unit when the judgment result of the fifth judgment module is yes, and trigger the sending unit;

The sixth judging module is used to judge whether the current stripe unit is the last stripe unit storing data when the judgment result of the fifth judging module is No;

The second output module is configured to output information prompting an error when the judgment result of the sixth judgment module is yes;

The increment module is configured to use the next stripe unit of the current stripe unit as the current stripe unit when the judgment result of the sixth judgment module is negative, and trigger the fourth generation module.

The data sending method and device of the RAID storage system provided by the present invention, the method includes: receiving the read command sent by the host, and finding the target stripe unit according to the read command; Whether the data in the target stripe unit is correct; if yes, send the data in the target stripe unit to the host; if not, use the parity check algorithm to restore the data in the target stripe unit, and enter the data in the target stripe unit Steps to send data to the host. It can be seen that when the RAID storage system receives the read command from the host, it will check the data of the corresponding target stripe unit, and only send the data to the host on the premise of ensuring that the data is correct, which not only avoids wrong data The transmission of data, and more importantly, it can ensure the validity of data transmission and improve the efficiency of transmission.

Description of drawings

In order to illustrate the embodiments of the present invention more clearly, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. As far as people are concerned, other drawings can also be obtained based on these drawings on the premise of not paying creative work.

Fig. 1 is the flowchart of the data transmission method of a kind of RAID storage system provided by the embodiment of the present invention;

FIG. 2 is a structural diagram of a host and a RAID storage system provided by an embodiment of the present invention;

3 is a schematic diagram of the distribution of a data volume and verification data on a RAID storage system provided by an embodiment of the present invention;

FIG. 4 is a schematic diagram of the distribution of another data volume and verification data on the RAID storage system provided by the embodiment of the present invention;

FIG. 5 is a flowchart of data transmission of another RAID storage system provided by an embodiment of the present invention;

FIG. 6 is a flow chart of another data sending method of a RAID storage system provided by an embodiment of the present invention;

FIG. 7 is a flow chart of step S13 provided by an embodiment of the present invention;

FIG. 8 is a structural diagram of a data sending device of a RAID storage system disclosed by an embodiment of the present invention.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

The core of the present invention is to provide a data sending method and device of a RAID storage system, which is used for how the controller can quickly and effectively provide correct data to the host when the host issues a read command, thereby ensuring the efficiency and effectiveness of the read. sex.

In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

FIG. 1 is a flowchart of a data sending method of a RAID storage system provided by an embodiment of the present invention. As shown in Figure 1, the data sending methods of the RAID storage system include:

S10: Receive a read instruction sent by the host, and find the target stripe unit according to the read instruction.

S11: Use a parity check algorithm to judge whether the data in the target stripe unit is correct; if yes, go to step S12; otherwise, go to step S13.

S12: Send the data in the target stripe unit to the host.

S13: Recover the data in the target stripe unit by using a parity check algorithm, and proceed to step S12.

FIG. 2 is a structural diagram of a host and a RAID storage system provided by an embodiment of the present invention. As shown in Figure 2, RAID storage system 10 carries out data interaction with host computer 12, has included a plurality of disks in RAID storage system 10, as shown in Figure 2, 16 (1)-16 (6) are all disks, RAID storage system 10 includes a RAID controller 18 for directly exchanging data with each disk. It can be understood that FIG. 2 is only a specific example, and does not mean that the RAID storage system 10 has only 6 disks.

RAID controller 18 may exist in the system in the form of a computer having one or more processors capable of processing data according to execution instructions stored on a readable medium. RAID controller 18 is capable of simultaneously reading data from disks 16(1)-16(6) simultaneously. Disks 16(1)-16(5) contain one or more data volumes. For the convenience of explanation, we assume that disks 16(1)-16(5) store a data volume. This assumption is for the convenience of explanation. There may be multiple data volumes in actual scenarios. In addition to storing data volumes, disks 16(1)-16(5) also store first parity data and disk 16(6) stores second parity data. The RAID storage system 10 is configured to receive various requests for data volumes from the host 12 . The RAID storage system 10 may also be configured to receive requests from other computer systems, which will not be detailed here.

When the RAID storage system 10 receives a read command, it first searches for the target stripe unit, that is, finds the stripe unit corresponding to the read command, and then judges whether the data in the target stripe unit is Correct, if it is correct, it means that the data written in the target stripe unit is correct and also the data desired by the host 12 , then the data is sent to the host 12 . On the contrary, if it is judged that the data in the target stripe unit is incorrect, it means that an error occurred in the process of writing data to the target stripe unit, and the data in the target stripe unit needs to be restored, so as to ensure that the data sent to the The data of the host computer 12 is correct data.

In the data sending method of the RAID storage system provided in this embodiment, when the RAID storage system receives a read instruction from the host, it will check the data of the corresponding target stripe unit, and only send the data to It not only avoids the sending of wrong data, but more importantly, it can ensure the validity of data sending and improve the sending efficiency.

In order to be more clear about the storage status of the disk, Figure 3 and Figure 4 are given. FIG. 3 is a schematic diagram of the distribution of data volumes and parity data on a RAID storage system according to an embodiment of the present invention. FIG. 4 is another schematic diagram of distribution of data volumes and parity data on a RAID storage system according to an embodiment of the present invention. Figure 3 and Figure 4 show two different distributions, which will be described in detail below. It should be noted that each disk includes multiple stripe units, and stripe units of different disks form multiple stripes.

For Figure 3

FIG. 3 shows the distribution of stripes S ₁ -S _max on disks 16(1)-16(6). Specifically: the four disks 16(1)-16(4) are used to store data, 16(5) is used to store the second parity data, and 16(6) is used to store the first parity data. Stripe units with the same serial number on different disks form a stripe. For example, stripe unit B _1,1 is the first stripe unit of 16(1), stripe unit B _1,2 is the first stripe unit of 16(2), and stripe unit B _1,3 is 16 The first stripe unit of (3), stripe unit B _1,4 is the first stripe unit of 16(4), and the stripe unit SP ₁ is the first stripe unit of 16(5), then Stripe unit B _1,1 , strip unit B _1,2 , strip unit B _1,3 , strip unit B _1,4 and strip unit SP ₁ constitute the first strip S ₁ , and so on A second strip S ₂ , a third strip S ₃ and a fourth strip S ₄ are obtained. 16(6) is used to store the first parity data, including a plurality of stripe units, and each stripe unit corresponds to each stripe unit in the disks 16(1)-16(4), that is, the disk 16( Each stripe unit in 1)-16(4) has its own first parity data, and the four stripe units on the same stripe share a second parity data. In FIG. 3 , the first parity data is represented by P _y,x , and the second parity data is represented by SP _y . Both y and x are positive integers starting from 1.

In a specific implementation, each stripe unit SP _y stores the second parity data calculated according to the stripe units B _y,1 -B _y,4 , and this data is calculated according to the stripe units B _y,1 - By _{y, the logic of 4} can also be calculated.

Each stripe _Sy has corresponding first parity data on disk 16(6). In Fig. 3, each first parity data is stored in units P _y,1 -P _y,4 , and each unit P _y,x has a corresponding stripe unit B _y,x . Each unit P _y,x stores the second parity data obtained by logic or calculation of the stripe unit B _y,x .

The data interaction process between the host computer 12 and the RAID storage system 10 is: the first and second parity data respectively obtained from P _{y, x} and SP _y can be updated in real time after each stripe unit is changed. For example, the RAID controller 18 receives a request from the host 12 to overwrite and write new data on the stripe unit B _{y ,x} . Read data, read the first and second parity data from P _{y, x} and SP _y . Next, the RAID controller 18 generates new second parity data for the stripe unit SP _y , which is based on the second parity data stored on the stripe unit SP _y and the new parity data received from the host The data is obtained from the stored data on the stripe unit B _y,x ; correspondingly, the RAID controller 18 also generates new first parity data for the unit P _y,x at the same time, and this data passes through the P _y,x The stored parity data is obtained from the new data obtained from the host 12 and the stored data on the stripe unit By _,x . The second parity data that RAID controller 18 newly generates on SP _y covers the second parity data that has been stored on SP _y , so that the first parity data that is newly generated on P _{y, x} covers The first parity data stored on P _y,x makes the newly received data on By _,x overwrite the stored data.

FIG. 5 is a flow chart of data transmission in another RAID storage system provided by an embodiment of the present invention. As shown in FIG. 5 , the steps that are the same as those in the above embodiment are not repeated in this embodiment. On the basis of the foregoing embodiments, step S11 specifically includes:

S110: Read the stored data of the target stripe unit and the stored first parity data corresponding to the target stripe unit.

S111: Generate new first parity data from the stored data of the target stripe unit according to the parity algorithm.

S112: Determine whether the stored first parity data is the same as the new first parity data.

Wherein, if yes, go to step S12, otherwise, go to step S13.

In another embodiment, step S13 specifically includes:

S130: Obtain the second parity data of the stripe where the target stripe unit is located and the stored data of the remaining stripe units of the stripe where the target stripe unit is located, and generate new parity data corresponding to the target stripe unit according to the parity algorithm. data.

S131: Generate new data corresponding to the target stripe unit and compare it with the first parity data according to the parity algorithm.

S132: Determine whether the compared first parity data is the same as the stored first parity data, if yes, go to step S133, otherwise, go to step S134.

S133: Overwrite the existing data of the target stripe unit with the new data corresponding to the target stripe unit, and proceed to step S12.

S134: Determine whether the new data corresponding to the target stripe unit is the same as the stored data of the target stripe unit, if yes, go to step S136, otherwise, go to step S135.

S135 : Output information prompting an error.

S136: Modify the first parity data corresponding to each stripe unit of the stripe where the target stripe unit is located according to the parity algorithm, and enter step S12.

When the RAID controller 18 receives a request to read data on the stripe unit B _y,x , as a response, the RAID controller 18 reads the stored data D _old on the stripe unit B _y,x . The stored first parity data P _old on the unit P _y,x . Next, the RAID controller 18 generates new first parity data P _new according to the stored data D _old . Wherein, the algorithm for generating P _new is the same as the algorithm for generating P _old on P _y,x in the disk 16(6). RAID controller 18 compares P _new with P _old , if the new first parity data P _new is different from the existing first parity data P _old , then it is considered that the requested data is damaged, and P _old is wrongly identified. Generated; when the new first parity data P _new is the same as P _old , it means that the data on the stripe unit By _,x can be returned to the host 12.

If P _new is not equal to P _old , then RAID controller 18 reads the data on the remaining stripe units except By _{, x} in this stripe, and the second parity data on the stripe unit SP _y , and generates The new data D _new corresponding to the target stripe unit, more specifically, the new data D _new corresponding to the target stripe unit is based on the data on the stripe unit B _y,1 -B _y,4 and the data on the stripe unit SP _y Second parity data generation. Then generate a comparison first parity data P' _{new according to the new data D new .} The algorithm used to generate P' _new is the same as the algorithm for generating P _new . Comparing P' _new and P _new , if P' _new and P _new are the same, then the existing data D _old on the stripe unit B _y,x is overwritten by D _new . However, when the additionally generated comparison first parity data P' _new is different from P _new , it is compared whether the new data D _new is equal to D _old .

If D _new is different from D _old after comparison, an error message is returned to the host 12, indicating that the RAID storage system 10 has excessive data damage.

If D _new is the same as D _old after comparison, it means that one or some first parity data in this stripe has an error, and needs to be repaired according to the parity algorithm. The specific repair process of each first parity data is:

Generate new parity data P _new(i) according to the stored data in the stripe unit B _y,x . The algorithm used to generate P _new is the same as that used to generate P _old on P _y,x . Then write P _new(i) to overwrite P _old(i) . The above process is repeated until all the first parity data in this stripe are modified. The subscript i indicates that multiple strip units are cyclically performed sequentially.

FIG. 5 shows that the RAID storage system 10 receives a read data request for stripe unit B _y,x only. However, if the RAID storage system 10 receives a request to read data from multiple stripe units, it will repeat the process in FIG. 5 once. In terms of time, the process in Figure 5 may take longer than the current technical process, but it increases the validity and reliability of the data returned to the host 12. Compared with the prior art, error data may be sent without limit Speaking, the time used by the method provided by the invention is also less, so to a certain extent, the efficiency is also higher.

For Figure 4

Where FIG. 4 is the same as FIG. 3 , this embodiment will not describe it again. Another kind of data is stored on the disk 16 ( 6 ), that is, a checksum. Checksum CS ₁ -CS _max corresponding to stripes S ₁ -S _max , in a system each checksum data CS _y is composed of stripe units B _y,1 -B _y,4 and stripe The SP _y corresponding to band S _y is calculated; the algorithm for generating CS _y is different from the algorithm for generating SP _y , and no matter what data form CS _y is, the data of any strip unit B _y,x can be Generated from data in CS _y and SP _y .

Like P _y,x , the checksum data CS _y is updated every time the stripe unit B _y,x changes. When the RAID controller 18 receives an overwrite request from the host computer 12 to the stripe unit B _{y, x} , the RAID controller 18 reads the existing data on the stripe unit B _{y, x} , and the second data on the SP _y Parity data, CS _y checksum; Then, RAID controller 18 according to the second parity data on the stripe unit SP _y , from the new data received from the host computer 12, and stripe unit B _{y, x} has stored The data of SP _y generates new second parity data. At the same time, RAID controller 18 will also generate a new checksum for CS _y based on the existing checksum on CS _y , the new data received from host 12, and the stored data on stripe unit B _y,x . Thus, RAID controller 18 overwrites the new second parity data on SP _y , the new checksum on CS _y , and the new data from host 12 on By _,x .

FIG. 6 is a flowchart of another data sending method of a RAID storage system provided by an embodiment of the present invention. As shown in FIG. 6, the same steps as those in the above-mentioned embodiment will not be repeated in this embodiment, and step S11 specifically includes:

S113: Calculate the second parity data of the stripe where the target stripe unit is located according to the parity algorithm.

S114: Determine whether the calculated second parity data is the same as the stored second parity data, if yes, go to step S12, otherwise, go to step S13.

FIG. 7 is a flow chart of step S13 provided by an embodiment of the present invention. As shown in Figure 7, step S13 specifically includes:

S137: Set the first stripe unit of the stripe where the target stripe unit is located as the starting unit.

S138: Generate the stored second parity data of the current stripe and the stored first parity data of the remaining stripe units in the stripe where the target stripe unit is located according to the parity algorithm to generate the corresponding data of the current stripe unit. new data.

S139: Generate a new checksum corresponding to the current stripe from the new data corresponding to the current stripe unit and the stored data of the remaining stripe units in the stripe where the target stripe unit is located.

S140: Determine whether the new checksum corresponding to the current stripe is the same as the stored checksum, if yes, go to step S141, otherwise go to step S142.

S141: Overwrite the stored data of the current stripe unit with the new data corresponding to the current stripe unit, and proceed to step S12.

S142: Determine whether the current stripe unit is the last stripe unit storing data, if yes, go to step S143, otherwise, go to step S144.

S143: Outputting error message;

S144: Use the next stripe unit of the current stripe unit as the current stripe unit, and return to step S138.

The RAID controller 18 accepts the read data request from the host 12, and the requested data is stored in the stripe unit B _y,x . The RAID controller 18 generates new second parity data P _new according to the data of the stripe units B _y,1 -B _y,4 . It should be noted that the generation algorithm of P _new is the same as that of generating the existing parity data P _old on the stripe unit SP _y . Then the RAID controller 18 compares P _new and P _old .

If P _new is equal to P _old , the data on the stripe unit _By,x is considered to be valid and sent to the host 12.

When P _new is different from P _old , it is considered that the damaged data exists in the stripe units B _y,1 -B _y,4 , and the data of each stripe unit needs to be restored. In a specific implementation, a dummy variable i may be set to restore the data of each stripe unit at a time, which will not be described in detail in this embodiment, see FIG. 6 .

In step S139, the RAID controller 18 generates a new checksum _CSnew . It is worth noting that the algorithm for generating CS _new is the same as the algorithm for generating CS ₁ -CS _max on disk 16(6).

In the above-mentioned embodiments, several embodiments corresponding to the data sending device of the RAID storage system are disclosed, and hereinafter, corresponding embodiments corresponding to the data sending device of the RAID storage system will be given. Since the data sending device of the RAID storage system corresponds to the data sending method of the RAID storage system, please refer to the description above for the specific implementation manner, and details will not be repeated in this embodiment. FIG. 8 is a structural diagram of a data sending device of a RAID storage system disclosed by an embodiment of the present invention. As shown in Figure 8, the device includes:

The search unit 1 is configured to receive the read instruction sent by the host, and find the target stripe unit according to the read instruction;

Judging unit 2, configured to use a parity check algorithm to judge whether the data in the target stripe unit is correct;

The recovery unit 3 is used to recover the data in the target stripe unit by using a parity check algorithm when the determination result of the determination unit is No;

The sending unit 4 is configured to send the data in the target stripe unit to the host when the judging result of the judging unit is yes, or after the data is restored by the restoring unit.

As a preferred embodiment, the judging unit 2 specifically includes:

A reading module, configured to read the stored data of the target stripe unit and the stored first parity data corresponding to the target stripe unit;

The first generation module is used to generate new first parity data from the stored data of the target stripe unit according to the parity algorithm;

The first judging module is used to judge whether the stored first parity data is the same as the new first parity data, and if so, trigger the sending unit; otherwise, trigger the recovery unit.

As a preferred embodiment, the recovery unit 3 specifically includes:

The second generation module is used to obtain the second parity data of the stripe where the target stripe unit is located and the stored data of the remaining stripe units of the stripe where the target stripe unit is located, and generate the target stripe according to the parity algorithm new data corresponding to the band unit;

The third generation module is used to generate new data corresponding to the target stripe unit and compare the first parity data according to the parity algorithm;

The second judging module is used to judge whether the first parity data is the same as the stored first parity data;

The first covering module is configured to overwrite the stored data of the target stripe unit with the new data corresponding to the target stripe unit when the judgment result of the second judging module is yes, and trigger the sending unit;

The third judging module is used to judge whether the new data corresponding to the target stripe unit is the same as the stored data of the target stripe unit when the judgment result of the second judging module is No;

The first output module is used to output information prompting an error when the judgment result of the third judging module is No;

The modification module modifies the first parity data corresponding to each stripe unit of the stripe where the target stripe unit is located according to the parity algorithm when the judgment result of the third judgment module is yes, and triggers the sending unit.

In another embodiment, the judging unit 2 specifically includes:

A calculation module, configured to calculate the second parity data of the stripe where the target stripe unit is located according to the parity algorithm;

The fourth judging module is used to judge whether the calculated second parity data is the same as the stored second parity data, if yes, trigger the sending unit, otherwise, trigger the recovery unit.

As a preferred embodiment, the recovery unit 3 specifically includes:

A setting module, configured to set the first strip unit of the strip where the target strip unit is located as the starting unit;

The fourth generation module is used to generate the current parity data from the stored second parity data of the current stripe and the stored first parity data of the remaining stripe units in the stripe where the target stripe unit is located according to the parity algorithm. The new data corresponding to the stripe unit;

The fifth generation module is used to generate a new checksum corresponding to the current stripe from the new data corresponding to the current stripe unit and the stored data of the remaining stripe units of the stripe where the target stripe unit is located;

The fifth judging module is used to judge whether the new checksum corresponding to the current stripe is the same as the existing checksum;

The second covering module is used to overwrite the stored data of the current stripe unit with the new data corresponding to the current stripe unit when the judgment result of the fifth judgment module is yes, and trigger the sending unit;

The sixth judging module is used to judge whether the current stripe unit is the last stripe unit storing data when the judgment result of the fifth judging module is No;

The second output module is used to output information prompting an error when the judgment result of the sixth judgment module is yes;

The increment module is configured to use the next stripe unit of the current stripe unit as the current stripe unit when the judgment result of the sixth judgment module is negative, and trigger the fourth generation module.

The data sending device of the RAID storage system provided in this embodiment, when the RAID storage system receives a read command from the host, will check the data of the corresponding target stripe unit, and only send the data to It not only avoids the sending of wrong data, but more importantly, it can ensure the validity of data sending and improve the sending efficiency.

The data sending method and device of the RAID storage system provided by the present invention have been introduced in detail above. Each embodiment in the description is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other. As for the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and for the related information, please refer to the description of the method part. It should be pointed out that for those skilled in the art, without departing from the principles of the present invention, some improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

Claims (10)

1. a kind of data transmission method for uplink of RAID storage system, it is characterised in that including：

The reading instruction that Receiving Host sends, and find target stripe unit according to the reading instruction；

Judge whether the data in the target stripe unit are correct using parity arithmetic；

If it is, by the data is activation in the target stripe unit to the main frame；

If it is not, then being recovered the data in the target stripe unit using the parity arithmetic, and enter institute The step of stating data is activation to the main frame in the target stripe unit.

2. the data transmission method for uplink of RAID storage system according to claim 1, it is characterised in that the utilization odd even school Checking method judges whether the data in the target stripe unit correctly specifically include：

Read the canned data of the target stripe unit and the target stripe unit is corresponding has deposited the first even-odd check Data；

The canned data of the target stripe unit is generated into new first parity data according to the parity arithmetic；

Whether the first parity data has been deposited in judgement identical with new first parity data；

Wherein, it is no if it is, the step of into data is activation to the main frame by the target stripe unit Then, into it is described the data in the target stripe unit are recovered using the parity arithmetic the step of.

3. the data transmission method for uplink of RAID storage system according to claim 2, it is characterised in that described using described strange Data in the target stripe unit are carried out recovery and specifically included by even parity check algorithm：

Obtain bar where second parity data and the target stripe unit of band where the target stripe unit The canned data of each stripe cell of remaining of band, and it is corresponding to generate the target stripe unit according to the parity arithmetic New data；

The corresponding new data generation of the target stripe unit is contrasted into the first even-odd check number according to the parity arithmetic According to；

Judge the first parity data of the contrast and whether described to have deposited the first parity data identical；

If it is, the corresponding new data of the target stripe unit is covered the canned data of the target stripe unit, and The step of into data is activation to the main frame by the target stripe unit；

If it is not, then judge the corresponding new data of the target stripe unit and the target stripe unit canned data whether It is identical；

If it is not, then the information of output prompting mistake；

If it is, right according to each stripe cell institute that the parity arithmetic changes band where the target stripe unit The first parity data answered, and enter the step of the data is activation by the target stripe unit to the main frame Suddenly.

4. the data transmission method for uplink of RAID storage system according to claim 1, it is characterised in that the utilization odd even school Checking method judges whether the data in the target stripe unit correctly specifically include：

The second parity data of band where the target stripe unit is calculated according to the parity arithmetic；

Whether the second parity data for being calculated of judgement is with to have deposited the second parity data identical；

Wherein, it is no if it is, the step of into data is activation to the main frame by the target stripe unit Then, into it is described the data in the target stripe unit are recovered using the parity arithmetic the step of.

5. the data transmission method for uplink of RAID storage system according to claim 4, it is characterised in that described using described strange Data in the target stripe unit are carried out recovery and specifically included by even parity check algorithm：

The first stripe cell for setting band where the target stripe unit is start element；

Current band the second parity data and the target stripe unit institute have been deposited into according to the parity arithmetic The corresponding new data of current stripe cell is generated in first parity data of having deposited of remaining each stripe cell of band；

By remaining each stripe cell of the corresponding new data of the current stripe cell and band where the target stripe unit Canned data generate the corresponding new verification of current band and；

Judge the corresponding new verification of the current band and verified and whether identical with having deposited；

If it is, by the canned data of the current stripe cell of the current corresponding new data covering of stripe cell, and enter The step of data is activation to main frame by the target stripe unit；

If it is not, then judge current stripe cell whether be last data storage stripe cell；

If it is, the information of output prompting mistake；If it is not, then using next stripe cell of current stripe cell as work as Preceding stripe cell, and return.

6. a kind of data sending device of RAID storage system, it is characterised in that including：

Searching unit, for the reading instruction that Receiving Host sends, and finds target stripe unit according to the reading instruction；

Judging unit, for judging whether the data in the target stripe unit are correct using parity arithmetic；

Recovery unit, for the judged result in the judging unit for it is no when, using the parity arithmetic by the mesh Data in mark stripe cell are recovered；

Transmitting element, for being yes in the judged result of the judging unit, or after the recovery unit is recovered data, By the data is activation in the target stripe unit to the main frame.

7. the data sending device of RAID storage system according to claim 6, it is characterised in that the judging unit tool Body includes：

Read module, for reading the canned data of the target stripe unit and the target stripe unit is corresponding has deposited First parity data；

First generation module, for according to the parity arithmetic by the canned data of target stripe unit generation new the One parity data；

First judge module, for judge to have deposited the first parity data and new first parity data whether phase Together, if it is, triggering the transmitting element, otherwise, the recovery unit is triggered.

8. the data sending device of RAID storage system according to claim 7, it is characterised in that the recovery unit tool Body includes：

Second generation module, the second parity data and the mesh for obtaining band where the target stripe unit The canned data of remaining each stripe cell of band where mark stripe cell, and generate the mesh according to the parity arithmetic The corresponding new data of mark stripe cell；

3rd generation module, for according to the parity arithmetic that the corresponding new data generation of the target stripe unit is right Than the first parity data；

Second judge module, for judge it is described contrast the first parity data be with first parity data of having deposited It is no identical；

First overlay module, during for the judged result in second judge module to be, by the target stripe unit pair The new data answered covers the canned data of the target stripe unit, and triggers the transmitting element；

3rd judge module, for when the judged result of second judge module is no, judging the target stripe unit Whether corresponding new data is identical with the canned data of the target stripe unit；

First output module, for when the judged result of the 3rd judge module is no, the information of mistake to be pointed out in output；

Modified module, with not when the judged result of the 3rd judge module is to be, according to parity arithmetic modification The first parity data where the target stripe unit corresponding to each stripe cell of band, and it is single to trigger the transmission Unit.

9. the data sending device of RAID storage system according to claim 6, it is characterised in that the judging unit tool Body includes：

Computing module, the second odd even school for calculating band where the target stripe unit according to the parity arithmetic Test data；

4th judge module, for judging the second parity data for being calculated and whether having deposited the second parity data It is identical, if it is, triggering the transmitting element, otherwise, trigger the recovery unit.

10. the data sending device of RAID storage system according to claim 9, it is characterised in that the recovery unit Specifically include：

Setup module, the first stripe cell for setting band where the target stripe unit is start element；

4th generation module, for current band have been deposited into the second parity data and institute according to the parity arithmetic The first parity data of having deposited for stating remaining each stripe cell of band where target stripe unit generates current stripe cell Corresponding new data；

5th generation module, for by the corresponding new data of the current stripe cell and band where the target stripe unit Remaining each stripe cell canned data generate the corresponding new verification of current band and；

Whether the 5th judge module, verify and identical for judging the corresponding new verification of the current band and with having deposited；

Second overlay module, the judged result for the 5th judge module is when being, by the current stripe cell correspondence New data cover the canned data of current stripe cell, and trigger the transmitting element；

6th judge module, for the 5th judge module judged result for it is no when, judge current stripe cell whether be The stripe cell of last data storage；

Second output module, during for the judged result in the 6th judge module to be, the information of output prompting mistake；

It is incremented by module, for when the judged result of the 6th judge module is no, by next of current stripe cell Tape cell triggers the 4th generation module as current stripe cell.